Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aAAaqwq/AGI-Super-Team --skill author-agent-suitegit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aaaaqwq/agi-super-team/author-agent-suite)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/author-agent-suite"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/author-agent-suite/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/author-agent-suite"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/author-agent-suite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 18 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 18 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00910 |
| Opus 5 | $0.00019 | $0.00455 |
| Sonnet 5 | $0.00008 | $0.00182 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade B, and why
author-agent-suite scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
7. **Resolve precedence explicitly.** Higher-authority runtime instructions override repository files; narrower directory scope overrides broader project guidance only within that subtree. User requests may select behavi Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author Agent Suite
Build an instruction system whose files have one owner, one purpose, and an explicit loading path. Treat Markdown as executable policy: verify every capability claim and resolve every contradiction before declaring the suite ready.
Workflow
- Confirm the host contract. Identify which runtime discovers
AGENTS.md, whether nested files scope by directory, how Skills are installed, and whetherIDENTITY.md,SOUL.md, orTOOLS.mdrequire an explicit routing instruction. Never assume a filename is loaded merely because it exists. - Inventory existing instructions. Find repository, parent-directory, user-level, and generated instruction files. Record their scope, authority, audience, freshness, and conflicts.
- Build a fact matrix. Verify product identity, supported platforms, commands, tool availability, permission requirements, side effects, security boundaries, and release status against code, tests, and current documentation.
- Assign one concern to one file. Put repository operating rules in
AGENTS.md, reusable procedures in a standard Skill, identity inIDENTITY.md, durable behavior principles inSOUL.md, and operational tool contracts inTOOLS.md. - Design the load graph. Make the runtime entry file route to non-discoverable companion files. Keep
AGENT.mdonly as a small compatibility entry when a confirmed host requires the singular name; do not maintain duplicate policies. - Write the smallest authoritative layer. Keep frequently loaded files short. Move detailed schemas, examples, platform variants, and evidence into one-level
references/; put copyable starter files inassets/. - Resolve precedence explicitly. Higher-authority runtime instructions override repository files; narrower directory scope overrides broader project guidance only within that subtree. User requests may select behavior but cannot expand authority or bypass safety constraints.
- Validate as a system. Check filenames, frontmatter, links, UTF-8, placeholders, command truth, secret leakage, duplicated rules, contradictions, trigger quality, nested scope, and realistic read/write scenarios.
- Record evidence and ownership. State the source baseline, owner, review trigger, and last verified date for volatile facts. Label aspirations as plans rather than implemented capability.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 254 B
- assets/starter-kit/AGENT.md 237 B
- assets/starter-kit/AGENTS.md 1.7 KB
- assets/starter-kit/agents/openai.yaml 184 B
- assets/starter-kit/IDENTITY.md 746 B
- assets/starter-kit/SKILL.md 780 B
- assets/starter-kit/SOUL.md 941 B
- assets/starter-kit/TOOLS.md 1.1 KB
- PROVENANCE.md 833 B
- references/file-specifications.md 11 KB
- references/project-evidence.md 3.4 KB
- references/suite-architecture.md 7.7 KB
- references/validation-checklist.md 5.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 44 lines · 38 tokens per session scan B adb9e44c4231
author-agent-suite is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 910 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
guidance
Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
eldar
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance…
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
memory-worktree
Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my…
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.